Load management system for device to optimize user experience

Abstract

A computer implemented method includes monitoring resource utilization for multiple programs running on a user device. A current user interaction with the programs is detected and a usage contextual profile representing user interaction with the programs is derived. The monitored resource utilization is compared to a performance threshold and one of the multiple programs is distributed for execution elsewhere in response to the comparing to optimize user experience on the user device in accordance with the usage contextual profile.

1 . A computer implemented method comprising:
 monitoring resource utilization for multiple programs running on a user device;   detecting current user interaction with the programs;   deriving a usage contextual profile representing user interaction with the programs;   comparing the monitored resource utilization to a performance threshold; and   distributing one of the multiple programs for execution elsewhere in response to the comparing to optimize user experience on the user device in accordance with the usage contextual profile.   
     
     
         2 . The method of  claim 1  wherein monitoring resource utilization includes tracking at least one of central processing unit (CPU) utilization or random access memory (RAM) utilization. 
     
     
         3 . The method of  claim 2  wherein the performance threshold is a percentage of CPU utilization. 
     
     
         4 . The method of  claim 1  wherein the derived usage contextual profile is derived as a function of most used program or programs. 
     
     
         5 . The method of  claim 4  wherein the most used program is derived as one of the multiple programs having a highest central processing unit (CPU) utilization over a just ending selected time window. 
     
     
         6 . The method of  claim 4  wherein distributing one of the multiple programs includes selecting a background program that is not associated with the derived usage contextual profile having a utilization rate higher than other background programs. 
     
     
         7 . The method of  claim 4  wherein distributing one of the multiple programs includes selecting one of the most used programs. 
     
     
         8 . The method of  claim 1  wherein distributing one of the multiple programs comprises distributing a portion of the one of the multiple programs. 
     
     
         9 . The method of  claim 1  wherein distributing one of the multiple programs comprises distributing multiple of the multiple programs. 
     
     
         10 . The method of  claim 1  wherein deriving a usage contextual profile representing user interaction with the programs comprises:
 comparing the current user interactions with the programs to user interactions with programs associated with multiple saved usage contextual profiles; and 
 selecting the saved usage contextual profile having user interactions with programs that is closest to the current user interactions with programs. 
 
     
     
         11 . The method of  claim 1  wherein the derived usage contextual profile is derived based on current usage features provided to a machine learning model trained to classify current usage as one of many usage contextual profiles. 
     
     
         12 . The method of  claim 11  wherein the machine learning model is trained as a function of labeled sets of usage features derived from user interaction data comprising logged user interaction data comprising user selections associated with executing programs. 
     
     
         13 . A machine-readable storage device having instructions for execution by a processor of a machine to cause the processor to perform operations to perform a method, the operations comprising:
 monitoring resource utilization for multiple programs running on a user device;   detecting current user interaction with the programs;   deriving a usage contextual profile representing user interaction with the programs;   comparing the monitored resource utilization to a performance threshold; and   distributing one of the multiple programs for execution elsewhere in response to the comparing to optimize user experience on the user device in accordance with the usage contextual profile.   
     
     
         14 . The device of  claim 13  wherein monitoring resource utilization includes tracking at least one of central processing unit (CPU) utilization or random access memory (RAM) utilization and wherein the performance threshold is a percentage of CPU utilization. 
     
     
         15 . The device of  claim 13  wherein the derived usage contextual profile is derived as a function of most used program or programs and wherein the most used program is derived as one of the multiple programs having a highest central processing unit (CPU) utilization over a just ending selected time window. 
     
     
         16 . The device of  claim 13  wherein deriving a usage contextual profile representing user interaction with the programs comprises:
 comparing the current user interactions with the programs to user interactions with programs associated with multiple saved usage contextual profiles; and 
 selecting the saved usage contextual profile having user interactions with programs that is closest to the current user interactions with programs. 
 
     
     
         17 . The device of  claim 13  wherein the derived usage contextual profile is derived based on current usage features provided to a machine learning model trained to classify current usage as one of many usage contextual profiles and wherein the machine learning model is trained as a function of labeled sets of usage features derived from user interaction data comprising logged user interaction data comprising user selections associated with executing programs. 
     
     
         18 . A device comprising:
 a processor; and   a memory device coupled to the processor and having a program stored thereon for execution by the processor to perform operations comprising:
 monitoring resource utilization for multiple programs running on a user device; 
 detecting current user interaction with the programs; 
 deriving a usage contextual profile representing user interaction with the programs; 
 comparing the monitored resource utilization to a performance threshold; and 
 distributing one of the multiple programs for execution elsewhere in response to the comparing to optimize user experience on the user device in accordance with the usage contextual profile. 
   
     
     
         19 . The device of  claim 18  wherein monitoring resource utilization includes tracking at least one of central processing unit (CPU) utilization or random access memory (RAM) utilization and wherein the performance threshold is a percentage of CPU utilization. 
     
     
         20 . The device of  claim 18  wherein deriving a usage contextual profile representing user interaction with the programs comprises:
 comparing the current user interactions with the programs to user interactions with programs associated with multiple saved usage contextual profiles; and 
 selecting the saved usage contextual profile having user interactions with programs that is closest to the current user interactions with programs.